Description
A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, delivering exceptional multimodal understanding and generation through heterogeneous MoE structures and modality-isolated routing. Supporting an extensive 131K token context length, the model achieves efficient inference via multi-expert parallel collaboration and quantization, while advanced post-training techniques including SFT, DPO, and UPO ensure optimized performance across diverse applications with specialized routing and balancing losses for superior task handling.
API Usage Examples
OpenAI Compatible Endpoint
Use this endpoint with any OpenAI-compatible library. Model: Baidu: ERNIE 4.5 21B A3B (baidu/ernie-4.5-21b-a3b)
curl https://api.ridvay.com/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d '{
"model": "baidu/ernie-4.5-21b-a3b",
"messages": [
{
"role": "user",
"content": "Explain the capabilities of the Baidu: ERNIE 4.5 21B A3B model"
}
],
"temperature": 0.7,
"max_tokens": 1024
}'Supported Modalities
- Text
API Pricing
- Input: 0.07$ / 1M tokens
- Output: 0.28$ / 1M tokens
Token Limits
- Max Output: 8,000 tokens
- Max Context: 120,000 tokens
Subscription Tiers
- free
- pro
- ultimate